• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 추계학술발표대회
• /
• pp.537-540
• /
• 2018

본 논문은 Jetson_TX2(임베디드 보드)의 ROS(Robot Operating System)기반으로 맵 지도를 작성하고, SLAM 및 DQN(Deep Q-Network)을 이용한 목적지까지의 이동명령(목표 선속도, 목표 각속도)을 자이로센서로 측정한 현재 각속도를 이용하여 Cortex-M3의 기반의 MCU(Micro Controllor Unit)에 하달하여 엔코더(encoder) 모터에서 측정한 현재 선속도와 자이로센서에서 측정한 각속도 값을 이용하여 PID제어를 통한 실내 자율주행 서비스 로봇.

• 한국정보기술학회 영문논문지
• /
• 제10권1호
• /
• pp.45-56
• /
• 2020

Despite extensive research, performance enhancement of keyphrase (KP) extraction remains a challenging problem in modern informatics. Recently, deep learning-based supervised approaches have exhibited state-of-the-art accuracies with respect to this problem, and several of the previously proposed methods utilize Bidirectional Encoder Representations from Transformers (BERT)-based language models. However, few studies have investigated the effective application of BERT-based fine-tuning techniques to the problem of KP extraction. In this paper, we consider the aforementioned problem in the context of scientific articles by investigating the fine-tuning characteristics of two distinct BERT models - BERT (i.e., base BERT model by Google) and SciBERT (i.e., a BERT model trained on scientific text). Three different datasets (WWW, KDD, and Inspec) comprising data obtained from the computer science domain are used to compare the results obtained by fine-tuning BERT and SciBERT in terms of KP extraction.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.140-142
• /
• 2020

본 논문에서는 심층적 강화학습 기반 GOP (Group of Picture) 크기를 선택하여 HEVC/H.265의 인코더를 제어하는 방법을 제안한다. 기존 방법에서는 현재 비디오 신호를 부호화 하는 과정에서 이미 부호화한 정보를 사용해야하는 부호화 의존성에 관한 문제가 있었다. 제안 방법은 강화학습 방식을 도입하여 이러한 문제를 극복하고 입력 비디오의 시간적 상관도에 따라 GOP의 크기를 적응적으로 선택하여 부호화 한다. 본 논문에서는 GOP 선택을 위한 강화학습 환경을 새롭게 정의하고 부호화 성능에 따른 보상을 부여하는 방식으로 학습을 수행한다. 제안된 적응적 GOP 선택에 따라 인코더 제어 시, 부호화 방법의 부호화 효율이 -6.07% BD-rate 향상된 실험 결과를 보이며 본 방법의 우수성을 입증한다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제62차 하계학술대회논문집 28권2호
• /
• pp.315-316
• /
• 2020

본 논문에서는 현재 이슈가 되고 있는 코로나에 대해서 사람들이 실생활에서 궁금해할 정보들을 Seq2seq 기술을 사용한 챗봇으로 정보를 제공한다.

• Nuclear Engineering and Technology
• /
• 제55권10호
• /
• pp.3716-3724
• /
• 2023

Loose parts monitoring and detecting alarm type in real Nuclear Power Plant have challenges such as background noise, insufficient alarm data, and difficulty of distinction between alarm data that occur during start and stop. Although many signal processing methods and alarm determination algorithms have been developed, it is not easy to determine valid alarm and extract the meaning data from alarm signal including background noise. To address these issues, this paper proposes a denoising autoencoder-based majority vote classification. Training and test data are prepared by acquiring alarm data from real NPP and simulation facility for data augmentation, and noisy data is reproduced by adding Gaussian noise. Using DAEs with 3, 5, 7, and 9 layers, features are extracted for each model and classified into neural networks. Finally, the results obtained from each DAE are classified by majority voting. Also, through comparison with other methods, the accuracy and the false alarm rate are compared, and the excellence of the proposed method is confirmed.

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.641-651
• /
• 2023

Malicious hate speech and gender bias comments are common in online communities, causing social problems in our society. Gender bias and hate speech detection has been investigated. However, it is difficult because there are diverse ways to express them in words. To solve this problem, we attempted to detect malicious comments in a Korean hate speech dataset constructed in 2020. We explored bidirectional encoder representations from transformers (BERT)-based deep learning models utilizing hyperparameter tuning, data sampling, and logits ensembles with a label distribution. We evaluated our model in Kaggle competitions for gender bias, general bias, and hate speech detection. For gender bias detection, an F1-score of 0.7711 was achieved using an ensemble of the Soongsil-BERT and KcELECTRA models. The general bias task included the gender bias task, and the ensemble model achieved the best F1-score of 0.7166.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1282-1290
• /
• 2017

Since the mitigation of fear of crime significantly enhances the consumptions in a city, studies focusing on urban safety analysis have received much attention as means of revitalizing the local economy. In addition, with the development of computer vision and machine learning technologies, efficient and automated analysis methods have been developed. Previous studies have used global features to predict the safety of cities, yet this method has limited ability in accurately predicting abstract information such as safety assessments. Therefore we used a Convolutional Context Neural Network (CCNN) that considered "context" as a decision criterion to accurately predict safety of cities. CCNN model is constructed by combining a stacked auto encoder with a fully connected network to find the context and use it in the CNN model to predict the score. We analyzed the RMSE and correlation of SVR, Alexnet, and Sharing models to compare with the performance of CCNN model. Our results indicate that our model has much better RMSE and Pearson/Spearman correlation coefficient.

• 한국멀티미디어학회논문지
• /
• 제24권1호
• /
• pp.21-29
• /
• 2021

With the recent increase in the number of households raising pets, various engineering studies have been underway for pets. The final purpose of this study is to automatically generate situation-sensitive captions that can express implicit intentions based on the behavior and sound of cats by embedding the already mature behavioral detection technology of pets as basic element technology in the video capturing research. As a pilot project to this end, this paper proposes a high-level capturing system using optical-flow, RGB, and sound information of cat videos. That is, the proposed system uses video datasets collected in an actual breeding environment to extract feature vectors from the video and sound, then through hierarchical LSTM encoder and decoder, to identify the cat's behavior and its implicit intentions, and to perform learning to create context-sensitive captions. The performance of the proposed system was verified experimentally by utilizing video data collected in the environment where actual cats are raised.

• 한국멀티미디어학회논문지
• /
• 제25권5호
• /
• pp.685-694
• /
• 2022

The goal of few-shot semantic segmentation is to build a network that quickly adapts to novel classes with extreme data shortage regimes. Most existing few-shot segmentation methods leverage single or multiple prototypes from extracted support features. Although there have been promising results for natural images, these methods are not directly applicable to the aerial image domain. A key factor in few-shot segmentation on aerial images is to effectively exploit information that is robust against extreme changes in background and object scales. In this paper, we propose a Mask-Guided Attention module to extract more comprehensive support features for few-shot segmentation in aerial images. Taking advantage of the support ground-truth masks, the area correlated to the foreground object is highlighted and enables the support encoder to extract comprehensive support features with contextual information. To facilitate reproducible studies of the task of few-shot semantic segmentation in aerial images, we further present the few-shot segmentation benchmark iSAID-, which is constructed from a large-scale iSAID dataset. Extensive experimental results including comparisons with the state-of-the-art methods and ablation studies demonstrate the effectiveness of the proposed method.

• 스마트미디어저널
• /
• 제11권10호
• /
• pp.65-75
• /
• 2022

딥러닝은 기존의 분석 모델이 갖는 한계를 극복하고 텍스트, 이미지, 음악 등 다양한 형태의 결과물을 생성할 수 있는 창의적인 도구로 활용되고 있다. 본 고에서는 Niko's MIDI Pack 음원 파일 1,609개를 데이터 셋으로 삼아 전처리 과정을 수행하고, 양방향 장단기 기억 순환 신경망(Bi-LSTM) 모델을 이용하여, 효율적으로 음악을 생성할 수 있는 전처리 방법과 예측 모델을 제시한다. 생성되는 으뜸음을 바탕으로 음악적 조성(調聲)에 적합한 새로운 시계열 데이터를 생성할 수 있도록 은닉층을 다층화하고, 디코더의 출력 게이트에서 인코더의 입력 데이터 중 영향을 주는 요소의 가중치를 적용하는 어텐션(Attention) 메커니즘을 적용한다. LSTM 모델의 인식률 향상을 위한 파라미터로서 손실함수, 최적화 방법 등 설정 변수들을 적용한다. 제안 모델은 MIDI 학습의 효율성 제고 및 예측 향상을 위해 높은음자리표(treble clef)와 낮은음자리표(bass clef)를 구분하여 추출된 음표, 음표의 길이, 쉼표, 쉼표의 길이와 코드(chord) 등을 적용한 다채널 어텐션 적용 양방향 기억 모델(Bi-LSTM with attention)이다. 학습의 결과는 노이즈와 구별되는 음악의 전개에 어울리는 음표와 코드를 생성하며, 화성학적으로 안정된 음악을 생성하는 모델을 지향한다.